{"id":"W763189797","doi":"10.3758/s13428-015-0614-z","title":"Performance impact of stop lists and morphological decomposition on word–word corpus-based semantic space models","year":2015,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Topic Modeling","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Natural language processing; Artificial intelligence; Word (group theory); Word lists by frequency; Space (punctuation); Semantics (computer science); Class (philosophy); Text corpus; Linguistics; Sentence","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005877975,0.0001742106,0.0003033041,0.000371337,0.0001266783,0.0001184222,0.0007325245,0.0001270629,0.00001022222],"category_scores_gemma":[0.0002446716,0.0001394171,0.00008855893,0.0005819659,0.000188641,0.0003713302,0.0003835248,0.0005196849,0.000006830026],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002219735,"about_ca_system_score_gemma":0.0002845323,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002890145,"about_ca_topic_score_gemma":0.00000317015,"domain_scores_codex":[0.9962441,0.001526323,0.0002907025,0.0005455705,0.000862723,0.0005305765],"domain_scores_gemma":[0.9977715,0.000553577,0.00008764344,0.0008291495,0.0003981663,0.0003599893],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0004010119,0.0008615559,0.0297658,0.0000847439,0.00002044998,0.0002112996,0.001218564,0.05064173,0.06080185,0.003297066,0.0002128328,0.8524831],"study_design_scores_gemma":[0.000665693,0.001038779,0.04704895,0.00007957193,0.000008146055,0.00004909426,0.00002181127,0.9372949,0.01212889,0.001458577,0.00002163706,0.0001839498],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6089865,0.00008903811,0.3902847,0.0001245495,0.00006140243,0.0002737973,0.000001913259,0.00004653174,0.0001316185],"genre_scores_gemma":[0.637554,0.00001625203,0.3622907,0.00001114933,0.00002061611,0.00004275223,0.000001775298,0.00000946407,0.00005321491],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8866532,"threshold_uncertainty_score":0.5685263,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.4101321547628593,"score_gpt":0.5636734972443137,"score_spread":0.1535413424814544,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}